{
  "abstract": "Background/Objectives: Architectural innovation is widely assumed to improve the cross-institutional generalization of tumor segmentation models, yet this is rarely tested. We compared three architectural families under an identical, leak-safe protocol in hepatocellular carcinoma (HCC) segmentation. Methods: Convolutional (nnU-Net ResEnc-M), state-space (U-Mamba Bot) and transformer (SwinUNETR) models were trained on HCC-TACE-Seg (n = 103) with identical patient-disjoint five-fold splits, then applied without adaptation to 3D-IRCADb (n = 15) and LiTS (n = 118). We assessed discrimination, case-level failure concordance, lesion-volume dependence, calibration and selective prediction. Results: Internal performance differed (Dice 0.685, 0.662, 0.479; Friedman p = 0.022) but external performance was low and largely convergent: the convolutional and state-space models were formally equivalent on both external cohorts (pre-specified margin ±0.05 Dice), whereas the transformer was inferior on LiTS (0.222; p < 0.0001) and inconclusive on 3D-IRCADb. Case-level Dice was highly concordant across all pairings (Spearman ρ = 0.84–0.96; 0.67–0.81 on LiTS after adjustment for lesion volume), the same cases failing across architectures. Lesion volume predicted performance in all six architecture × cohort combinations; lesions < 5 mL failed completely in 61–76% of cases and formed 1.9% of the development cohort against 31.4% of LiTS. Neither liver-mask constraint nor ensembling recovered performance. Deferring the 30% least-confident LiTS cases raised Dice to 0.516 (0.450 when only empty predictions were removed). Conclusions: Under a single-source, TACE-treated HCC training regime, cross-dataset failure of liver-tumor segmentation was governed primarily by lesion size rather than by architectural family; confidence-based selective prediction offers a deployable mitigation.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Biostatistics and Medical Informatics, Faculty of Medicine, Adıyaman University, 02040 Adıyaman, Türkiye",
    "Department of Biostatistics and Medical Informatics, Faculty of Medicine, İnönü University, 44280 Malatya, Türkiye",
    "Department of Surgery and Liver Transplantation, Faculty of Medicine, İnönü University, 44280 Malatya, Türkiye"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Hüseyin Kutlu",
      "orcid": "0000-0003-0091-9984"
    },
    {
      "affs": [
        1
      ],
      "name": "Cemil Çolak",
      "orcid": "0000-0001-5406-098X"
    },
    {
      "affs": [
        1,
        2
      ],
      "name": "Sami Akbulut",
      "orcid": "0000-0002-6864-7711"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9w3cmb8gcbfv5.bib",
  "cited_by": 0,
  "doi": "10.3390/cancers18203362",
  "fulltext_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13702596/?tool=EBI",
  "id": "9w3cmb8gcbfv5",
  "issns": [
    "2072-6694"
  ],
  "landing_url": "https://www.mdpi.com/2072-6694/18/20/3362",
  "language": "eng",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1707|Medical Image Segmentation Techniques"
    ]
  ],
  "openalex": "W7222971306",
  "pdf_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13702596/pdf/?tool=EBI",
  "pmcid": "PMC13702596",
  "pmid": null,
  "published": "2026-10-01",
  "publisher": "MDPI AG",
  "ris": "https://research.draconitic.com/paper/9w3cmb8gcbfv5.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:58Z",
      "native_id": "10.3390/cancers18203362",
      "source": "crossref",
      "url": "https://www.mdpi.com/2072-6694/18/20/3362"
    },
    {
      "first_seen": "2026-10-30T12:21:47Z",
      "native_id": "PMC:PMC13702596",
      "source": "europepmc",
      "url": "https://europepmc.org/article/PMC/PMC13702596"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "issn:2072-6694",
      "subfield": "oncology"
    }
  ],
  "title": "Convolutional, State-Space and Transformer Liver-Tumor Segmentation Models Trained on Hepatocellular Carcinoma Fail on the Same External Cases: Lesion Size Outweighs Architecture in Cross-Dataset Generalization",
  "title_text": "Convolutional, State-Space and Transformer Liver-Tumor Segmentation Models Trained on Hepatocellular Carcinoma Fail on the Same External Cases: Lesion Size Outweighs Architecture in Cross-Dataset Generalization",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:21:47Z",
  "url": "https://research.draconitic.com/paper/9w3cmb8gcbfv5",
  "venue": "Cancers",
  "versions": []
}